© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10170
    Prev
    Next
    INDEX
    Explanations

    words related to childbirth and prenatal health.

    oai_token-act-pair · gemini-2.0-flash

    terms related to medical risk factors

    np_token-act-pair-logits · gpt-4o-mini

    Medical/Scientific texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    providedIn
    -0.71
     skär
    -0.60
    principalColumn
    -0.56
     NPY
    -0.55
    creativecommons
    -0.55
     RoutedEventArgs
    -0.54
    Enllaces
    -0.53
     químicas
    -0.53
     varandra
    -0.52
     hardest
    -0.51
    POSITIVE LOGITS
    Lähteet
    0.49
     grav
    0.48
     CLIENT
    0.48
    Begriffsklä
    0.47
    ENODEV
    0.46
     الرياضيه
    0.46
    KommentareTeilen
    0.45
     al
    0.45
     cáo
    0.44
     Fet
    0.44
    Activations Density 3.108%

    No Known Activations